add model
Browse files- README.md +55 -0
- config.json +24 -0
- pytorch_model.bin +3 -0
README.md
CHANGED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
|
| 3 |
+
model-index:
|
| 4 |
+
- name: test-squad-trained
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 8 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 9 |
+
|
| 10 |
+
# test-squad-trained
|
| 11 |
+
|
| 12 |
+
This model was trained from scratch on an unkown dataset.
|
| 13 |
+
It achieves the following results on the evaluation set:
|
| 14 |
+
- Loss: 1.2026
|
| 15 |
+
|
| 16 |
+
## Model description
|
| 17 |
+
|
| 18 |
+
More information needed
|
| 19 |
+
|
| 20 |
+
## Intended uses & limitations
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Training and evaluation data
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
### Training hyperparameters
|
| 31 |
+
|
| 32 |
+
The following hyperparameters were used during training:
|
| 33 |
+
- learning_rate: 2e-05
|
| 34 |
+
- train_batch_size: 16
|
| 35 |
+
- eval_batch_size: 16
|
| 36 |
+
- seed: 42
|
| 37 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 38 |
+
- lr_scheduler_type: linear
|
| 39 |
+
- num_epochs: 3
|
| 40 |
+
|
| 41 |
+
### Training results
|
| 42 |
+
|
| 43 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 44 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 45 |
+
| 0.988 | 1.0 | 5486 | 1.1790 |
|
| 46 |
+
| 0.7793 | 2.0 | 10972 | 1.2026 |
|
| 47 |
+
| 0.8068 | 3.0 | 16458 | 1.2026 |
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
### Framework versions
|
| 51 |
+
|
| 52 |
+
- Transformers 4.6.1
|
| 53 |
+
- Pytorch 1.8.1+cu101
|
| 54 |
+
- Datasets 1.6.2
|
| 55 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-multilingual-cased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForQuestionAnswering"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "distilbert",
|
| 14 |
+
"n_heads": 12,
|
| 15 |
+
"n_layers": 6,
|
| 16 |
+
"output_past": true,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"qa_dropout": 0.1,
|
| 19 |
+
"seq_classif_dropout": 0.2,
|
| 20 |
+
"sinusoidal_pos_embds": false,
|
| 21 |
+
"tie_weights_": true,
|
| 22 |
+
"transformers_version": "4.6.1",
|
| 23 |
+
"vocab_size": 119547
|
| 24 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:024798d25cbc48d2fc6daaf24490b8d1d36dff09d36202c7aff5ef910852cb58
|
| 3 |
+
size 538984901
|